Often, when I use generative AI to produce videos, the results are close to what I envision but rarely capture my imagination exactly. Prompting the AI to fix specific details can be a cumbersome and time-consuming process. To address this, I'm developing solutions that make the creative workflow more intuitive. So far, I’ve built an app that allows users to provide visual clues as guides, along with a 3D environment where the camera can be freely manipulated within the generated scene.
The community is moving fast though. Now higgsfield allows using arrows and pointers to edit the video but so far, no one is doing a good camera control visually.
I was scrolling and everything on the hardware looked great (although I was looking for how the tech is different from e-ink, not how better its properties are).
Then I reached "Introducing Sol:OS" and stopped right there. Didn't look further and closed the tab. I'm skeptical when it comes to custom OS. Not a lot of startups can handle a hardware+software company. Hardware is hard enough. Software is second class citizen and doesn't get regular updates after a few years.
Not comparing here, but I just remembered that the first paper on graphene was rejected (twice) and one of the reviewers said something like 'this paper does not represent a scientific advance.'
> I don't need to trade that for need to spend time to know what and more importantly why something is where it is.
I had two options: 1. Learn everything first and then start prototyping. 2. Start prototyping and learn along the way. I chose the latter. But instead of searching stackoverflow and putting the pieces together, I used GPT and learned from the generated outputs in the context of my own problem.
It may not save a lot of time in larger projects because as you said, one should ultimately learn the "what and why", but it definitely provides a more pleasing experience. And I guess the time-saving part becomes more relevant with better tooling, like the suggestion I had.
For smaller pieces, you are right. But as a BE engineer, I was prototyping a concept and I didn't know much about Typescript+React+React-Router-Dom+React-Hooks-Form, etc etc. So I listed the libraries, a few lines of boilerplate and API definitions that RTK toolkit generated for me. Then asked GPT to generate the full page. It was much faster than I could "code it myself".
And that's why it is a "pain point". These all can be done automatically.
In my experience working with GPT4, if I give enough context on types, other functions definitions and the libraries I use, I get very accurate results. But it is a tedious task to copy paste from multiple places (type definitions, function definitions, packages, etc.).
In addition to the selected lines, does Continue support getting related definitions from the language server and inject them in the prompt? That would be huge.
The cost aside, I'm wondering how fly or heroku support their customers when they grow to microservices ecosystems.
The problem shifts from deploying easily to deploying reliably meaning one release of a service should not break the other services. Other problems appear too, like service discovery, peer authentication, gateways, test and staging environments where there are downstream dependencies, etc.
Are customers supposed to leave when they grow to this level? Or are there solutions for these?
The community is moving fast though. Now higgsfield allows using arrows and pointers to edit the video but so far, no one is doing a good camera control visually.